Person
Scott Nowson
Scott Nowson is a PwC specialist who spoke on a podcast about using machine learning to cut false alarms in bank anti-money laundering checks. He described a bank that received about 10,000 transaction-monitoring alerts a month, typically with less than 1 percent involving real fraud or money laundering.
Nowson said each alert takes a human agent at least 20 to 30 minutes to review. He also said deep learning is unsuitable because banks must explain missed cases to regulators, and he recommended decision trees instead. He said PwC achieved a 50 percent reduction in false positives with only two errors, beating the bank's 40 percent target.
1 episodes · 19 quoted claims
A bank that approached PwC reported receiving about 10,000 transaction-monitoring alerts a month, of which typically less than 1 percent involved real fraud or money laundering.
“we're getting 10 ,000 a month. And when you look into the data, the amount of actual fraud, of true money laundering, of a suspicious activity is typically less than 1%.”
AI in Financial Services · 0:03:51
Scott Nowson says each alert takes a human agent at least 20 to 30 minutes to review, so clearing the false positives requires a large team.
“with a human agent having to look at the 99 % and each one taking a minimum 20 to 30 minutes, that's a huge team that you need to look at this”
AI in Financial Services · 0:03:51
PwC builds transaction monitoring rules with its forensic experts and implements the systems that watch all transactions passing through a bank.
“we will build, using our forensic experts, some of the transaction monitoring rules and implement the transaction monitoring systems that are essentially watching everything that goes through a bank.”
AI in Financial Services · 0:03:20
Scott Nowson says that labeling every alert as a false alarm would give 99 percent accuracy, which shows why accuracy alone is a poor goal for finding rare real cases.
“You'll get a 99 % accuracy rate when you say everything's wrong and that just doesn't work.”
AI in Financial Services · 0:05:10
Scott Nowson says he learned to start by understanding the problem while working at Xerox alongside ethnographers, and applied this by sitting with real investigation agents.
“something I learned over the years working at Xerox and working with ethnographers was just understand the problem.”
AI in Financial Services · 0:05:10
Scott Nowson says human investigators typically review only about the last six transactions, while machine learning can scan two years of data in seconds.
“the human can only look at like the last six transactions. The whole point about machine learning is big data. It can look over two years in seconds and it can see much bigger patterns.”
AI in Financial Services · 0:06:12
Scott Nowson says true positives were so varied that roughly 10 to 20 percent of alerts would still need investigation to find the 1 percent that is real.
“it really needs the 10 to 20 % should still be investigated to find the 1%.”
AI in Financial Services · 0:08:03
Scott Nowson says deep learning is unsuitable for anti-money laundering because banks must explain to regulators at any audit why they missed a case.
“But you can't do deep learning in this environment because compliance. You have to be able to go to the regulator and say at any point being audited why you missed that.”
AI in Financial Services · 0:08:55
Scott Nowson mentions that MIT produced work on image classification that explains what each neuron in a neural network does.
“I think MIT came out with something for image classification that can explain what each neuron is doing in the network.”
AI in Financial Services · 0:08:55
Scott Nowson recommends decision tree algorithms for this work because they can be unfolded into explicit rules that regulators can audit.
“you take something like a decision tree algorithm, something which can essentially fold out into rules.”
AI in Financial Services · 0:08:55
Scott Nowson says many transaction monitoring rules rely on fixed thresholds, which customers eventually cross as their finances grow, producing alerts.
“So a lot of the transaction monitoring rules are about having a threshold. And finances change over time. We make more money, we spend more money. At some point, we pass the threshold.”
AI in Financial Services · 0:10:58
Scott Nowson says PwC has done similar deployments in banks in Europe, where it begins by modeling normal behavior in the data.
“and we've done similar things in banks in Europe, is we start looking at the normal and we start looking at the data”
AI in Financial Services · 0:10:58
Scott Nowson says PwC typically applies its machine learning layer to filter alerts before the bank's transaction monitoring output is reviewed, and uses it to suggest new detection rules.
“What we've typically done then is we've taken this post-transaction monitoring system and applied it before the transaction monitoring is done.”
AI in Financial Services · 0:11:27
One bank PwC worked with set a 40 percent reduction in false positives as the target that made up its business case.
“One of the banks we worked with set out, they want 40 % reduction in the false positives that for them was the business case”
AI in Financial Services · 0:13:01
PwC's rollout began with statistical testing of error rates and then moved to a semi-live beta that ran without interrupting the existing workflow.
“So the statistical confidence first, then it's going semi live, almost beta with the system where you don't interrupt the workflow.”
AI in Financial Services · 0:16:01
In the shadow phase of PwC's project, humans still investigated every alert while each was tagged with the algorithm's prediction.
“Every alert is still investigated by a human, but it's now tagged with what the algorithm would have predicted.”
AI in Financial Services · 0:16:01
Scott Nowson says PwC assumed the bank would want zero errors in the pilot, but stakeholders turned out to tolerate some errors.
“But we assumed they would also want no errors in the pilot. No, they were able to tolerate some errors.”
AI in Financial Services · 0:18:12
In the pilot phase PwC's approach identified 20 percent of false positives with no errors.
“we hit like in the pilot phase, 20 % false positive identification with no errors.”
AI in Financial Services · 0:18:12
With one data set and one banking segment, PwC achieved a 50 percent reduction in false positives with only two errors, exceeding the 40 percent target.
“We were actually able to get with one data set with one particular banking segment, 50 % reduction in false positives, with it turns out only two errors.”
AI in Financial Services · 0:18:12